Instructions to use npario/Swift-Qwen3.8-27B-MLX-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use npario/Swift-Qwen3.8-27B-MLX-4bit with MLX:

# Make sure mlx-vlm is installed
# pip install --upgrade mlx-vlm

from mlx_vlm import load, generate
from mlx_vlm.prompt_utils import apply_chat_template
from mlx_vlm.utils import load_config

# Load the model
model, processor = load("npario/Swift-Qwen3.8-27B-MLX-4bit")
config = load_config("npario/Swift-Qwen3.8-27B-MLX-4bit")

# Prepare input
image = ["http://images.cocodataset.org/val2017/000000039769.jpg"]
prompt = "Describe this image."

# Apply chat template
formatted_prompt = apply_chat_template(
    processor, config, prompt, num_images=1
)

# Generate output
output = generate(model, processor, formatted_prompt, image)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps Settings
LM Studio

How to use npario/Swift-Qwen3.8-27B-MLX-4bit with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "npario/Swift-Qwen3.8-27B-MLX-4bit"

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "mlx-lm": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "npario/Swift-Qwen3.8-27B-MLX-4bit"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent

How to use npario/Swift-Qwen3.8-27B-MLX-4bit with Hermes Agent:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "npario/Swift-Qwen3.8-27B-MLX-4bit"

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default npario/Swift-Qwen3.8-27B-MLX-4bit

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use npario/Swift-Qwen3.8-27B-MLX-4bit with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "npario/Swift-Qwen3.8-27B-MLX-4bit"

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "npario/Swift-Qwen3.8-27B-MLX-4bit" \
  --custom-provider-id mlx-lm \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

Swift-Qwen3.8-27B-MLX-4bit

MLX 4bit (affine, group size 32) quantized variant of ukisai/Swift-Qwen3.8-27b (text tower quantized; vision tower and projector retained in BF16) for Apple silicon via mlx-lm.

Provenance

Source: ukisai/Swift-Qwen3.8-27b @ revision 048328f4059015b63f860a453bf94834af0db683 (Swift Open License v1.0 for the UkisAI contribution + Apache-2.0 for the Qwen base (upstream LICENSE, LICENSE-APACHE-2.0, NOTICE)).
Quantized with mlx_lm.convert (mlx-lm 0.31.3): affine, 4-bit, group size 32.

Smoke gate

Before upload this pack passed a deterministic coherence gate: greedy 48-token chat generation loaded through mlx_lm.load, judged for emptiness, repetition loops, multi-script gibberish, and special-token debris. Verdict: ok.

Usage

pip install mlx-lm
mlx_lm.generate --model majentik/Swift-Qwen3.8-27B-MLX-4bit --prompt "Hello"

Evaluation

Coherence smoke gate only at publish time (see Smoke gate above). Per-tier gate records live in majentik/garden-quant-bench; perplexity / benchmark rows are added here when measured.

License

This pack is a quantized (Object-form) redistribution of ukisai/Swift-Qwen3.8-27b and inherits its dual licensing unchanged:

the Qwen/Qwen3.8-27B base weights remain under Apache-2.0 (LICENSE-APACHE-2.0);
the UkisAI Swift contribution (finetune) is under the Swift Open License v1.0 (LICENSE), which is free for research and commercial use by organisations with up to US$1M gross annual revenue; larger organisations need a Swift Enterprise License from UkisAI.

LICENSE, LICENSE-APACHE-2.0 and NOTICE are shipped verbatim in this repository as required by Section 4 (Redistribution) of the Swift Open License. The only change from upstream is the MLX quantization described above.

Available tiers

Repo	Quant
majentik/Swift-Qwen3.8-27B-MLX-2bit	2bit
majentik/Swift-Qwen3.8-27B-MLX-3bit	3bit
majentik/Swift-Qwen3.8-27B-MLX-4bit	4bit
majentik/Swift-Qwen3.8-27B-MLX-5bit	5bit
majentik/Swift-Qwen3.8-27B-MLX-6bit	6bit
majentik/Swift-Qwen3.8-27B-MLX-8bit	8bit
majentik/Swift-Qwen3.8-27B-MLX-MXFP4	MXFP4

Downloads last month: 140

Safetensors

Model size

27B params

Tensor type

U32

BF16

MLX

Hardware compatibility

4-bit

Model tree for npario/Swift-Qwen3.8-27B-MLX-4bit

Base model

Qwen/Qwen3.8-27B

Finetuned

ukisai/Swift-Qwen3.8-27b

Quantized

(55)

this model